ads-dna

Extract a public-safe brand and offer profile for paid advertising from an authorized website and operator input. Triggers on: brand DNA, brand profile, brand identity, brand style, brand colors, brand voice, visual identity, style guide, website brand analysis.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exceptionally lean, well-organized workflow with explicit authorization and validation checkpoints appropriate to guarded web fetching. Its main limitation is that guidance is instructional rather than executable, with no explicit error-recovery feedback loop.

Suggestions

Add a brief validate-fix-retry feedback loop (e.g., if URL validation or atomic write fails, diagnose and retry before proceeding) to lift workflow_clarity to 5.

Name the concrete tool/mechanism for the guarded fetch and screenshot and for the atomic write so the guidance is executable rather than only instructional.

Optionally preview the profile's component fields in the description to improve specificity.

Dimension	Reasoning	Score
Conciseness	The body is a lean six-step list plus a one-line disclaimer with no over-explanation of concepts Claude already knows; every line carries a distinct instruction, matching the lean-and-efficient top anchor.	5 / 5
Actionability	Steps give concrete, specific guidance (exact fields to observe in step 3, exact data to avoid collecting in step 5, atomic write to the run state directory in step 6), but as an instruction-only skill it stops short of fully executable commands/tools, placing it at mostly-executable rather than copy-paste ready.	4 / 5
Workflow Clarity	A clear numbered sequence 1-6 with validation checkpoints present (validate the URL before fetching in step 1, validate-and-write atomically in step 6), so it is not capped at 3; however, there is no explicit validate-fix-retry feedback loop for recovery, keeping it below 5.	4 / 5
Progressive Disclosure	This is a short single-purpose skill under 50 lines with no bundle files and no need for external references, and the content is well-organized as a numbered list, so the simple-skill exception lets it score 5.	5 / 5
	Total	18 / 20 Passed

Description

90%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and cleanly answers both what the skill does and when to use it, with strong natural trigger coverage and a distinctive niche. Its only weakness is that the single named action ("extract a profile") is high-level and does not preview the profile's component fields.

Dimension	Reasoning	Score
Specificity	"Extract a public-safe brand and offer profile for paid advertising from an authorized website and operator input" names the domain and one concrete action (extract a profile), matching the anchor that names the domain with 1-2 concrete actions but is not comprehensive; it does not enumerate the component fields the body later lists, so it is not a 4.	3 / 5
Completeness	It explicitly states what ("Extract a public-safe brand and offer profile...") and when ("Triggers on: ...") with concrete trigger phrases, satisfying the anchor for a clear explicit what-and-when; the equivalent trigger guidance means it is not capped at 3.	5 / 5
Trigger Term Quality	"Triggers on: brand DNA, brand profile, brand identity, brand style, brand colors, brand voice, visual identity, style guide, website brand analysis" provides comprehensive coverage of natural phrases and synonyms a user would actually say, matching the top anchor.	5 / 5
Distinctiveness Conflict Risk	The niche is specific (public-safe brand/offer profile for paid advertising from an authorized website) with distinct triggers like "brand DNA" and "website brand analysis", giving minimal overlap with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: AgriciDaniel/claude-ads
Path: skills/ads-dna/SKILL.md
Commit: 669c760

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.